© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 29863
    Prev
    Next
    INDEX
    Explanations

    amid circumstances

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    alley
    -0.10
    athan
    -0.09
    ish
    -0.09
    Ñıв
    -0.09
    aps
    -0.09
    å²Ĥ
    -0.08
     noqa
    -0.08
    æĢ»ä¹ĭ
    -0.08
    æ¼
    -0.08
    åĩ¡äºĭ
    -0.08
    POSITIVE LOGITS
    åIJĦç§į
    0.12
    æµĵæµĵ
    0.11
    åIJĦç§įåIJĦæł·
    0.11
    ä¸įæĸŃçļĦ
    0.10
    /out
    0.10
    çĥŃçĥĪ
    0.10
    å©Ĩ
    0.10
     Ñģобой
    0.10
    å©Ĩå©Ĩ
    0.10
    Ľå»º
    0.10
    Activations Density 0.008%

    No Known Activations